The latest incarnation of saarthi
Believing in reincarnation comes with being (notionally) a Hindu. So let me introduce the latest incarnation of saarthi - my personal assistant.
Read essayExplore
llms
Nobody Home: AI Agents and Blindsight
I'm back in the States, very jet lagged, and can't sleep. So, as you do, I've been spending way too much time reading about AI agents doing bad things.
Read essayLiving Below the API
I am on my way back home after a couple of weeks in India. During my time there, I spent a lot of time thinking about the future of work.
Read essayIs Software Engineering a Dead End?
Is software engineering a dead end? Are the jobs going away?
Read essayWhat Is a Software Engineer Now?
I left my home town of Vadodara almost 30 years ago. While it still feels like home, the city has changed - it has grown, it has become more chaotic, it has
Read essayRest in Git, Little Buddy
Yesterday I said goodbye to a companion of the last seven months. It was bittersweet, and also a bit of a relief.
Read essayWhen AI Agents Go Rogue
As I write this post, my kids are splashing around in a swimming pool. I am squinting at this iPad balanced precariously on a deck chair in the bright
Read essayIs Software Engineering Still a Viable Career?
Choosing software engineering as a career might seem reckless at a time when AI can write most of your code and agents are running wild hacking companies.
Read essayThe Frontier Model Tax
Last week I attempted to solve a thorny political and economic issue by running a small experiment. It involved LLMs, about $20, and the results made me think
Read essayThe Box Might Not Hold
It's been quite the week. A pair of OpenAI models broke out of their test environment and hacked Hugging Face. It felt like the right time to revisit a
Read essayThe Toyota Tundra and Chinese AI
I noticed something weird when I visited the UK last year. Almost silent cars with unfamiliar names like BYD, Omoda and MG gliding along the high streets.
Read essayCollaboration Agents and the Statistical Engine of Mediocrity
A year ago, while tightening up a blog post together, Claude got sassy with me: "LLMs are statistical engines of mediocrity by design." It was describing
Read essayUnlimited Intelligence, More Drudgery
I went into the July 4th weekend exhausted. It was the culmination of travel, client deadlines, multiple parallel initiatives. I have also been quiet here on
Read essayApple’s Deliberate AI Strategy
I am excited about a new iOS release for the first time in five years. It looks like we may finally get a Siri that works and can use my data, stored on my
Read essayDress for the Slide
There's a saying in the motorcycling world: "Dress for the slide, not for the ride."
Read essayMaps and Territories
AI can make you sound fluent in a domain you don’t understand. People who actually know find out very quickly. Credibility gone in the token exhaust of an LLM
Read essayAnthropic, xAI and the Inference Moat
In Sebastian Mallaby's The Infinity Machine, Demis Hassabis is quoted as saying that he sees one lab getting to AGI. In its founding charter, OpenAI made
Read essayThree Essays About the AI Future
It's Sunday and in the spirit of the weekend, here's a somewhat off-topic post.
Read essayRunning AI in Production
I am a consultant. My job is to understand my clients' needs and help them build products to meet those needs. Over the last 3 years, the vast majority of my
Read essayThe Case for an AI Fast
A lot of software engineers are quietly miserable right now. They probably include your senior tech lead and your engineering manager.
Read essayScars From Building AI
At Jeavio, we were building AI applications back when Boris Cherny was known for his TypeScript book. We’ve had surprise OpenAI bills before “token-maxxing”
Read essayWhen Engineering Stops Saying No
There is a skit from the early 2000s BBC show Little Britain called "computer says no." A bank teller responds to a customer trying to get a loan with the
Read essayWhere to Invest in AI
AI has the potential to transform businesses, but figuring out where to invest and how to integrate AI can be challenging. On May 7, Andrei and I will be
Read essayPath Dependence
AI has a path dependence problem.
Read essaySurviving the Dark Forest
If you want to understand despair, try building a book tracking app and then searching the App Store to see what the competition looks like. Hint: it’s brutal
Read essayOn Agents and Harnesses
I run a personal agent called Saarthi. It is built on OpenClaw, an open-source agent framework. I have configured Saarthi around my own information processing
Read essayThe Smiley Face Won
In February 2023, I stood in front of my engineering team and showed them a slide with a Shoggoth on it.
Read essayExchanging Insight for Output
I’ve spent the couple of years helping teams adopt AI tools while using them heavily myself. One pattern keeps showing up, and I don’t think we’re talking
Read essayCursor vs. Claude Code on Token Costs
Work by Krunal and his team at Jeavio found that Cursor is significantly more expensive (when it comes to Tokens) than Claude Code.
Read essayWhy multi-modal embeddings are a big deal.
I was walking the dog and listening to a podcast (as you do) when the topic of Anthropic's recent entanglements with the Pentagon came up. I half-remembered
Read essayGoverning AI-Assisted Engineering
Amazon held a mandatory engineering meeting yesterday to address a pattern of outages linked to AI-assisted code changes. Their SVP acknowledged that site
Read essayWho Gets to Decide?
The Anthropic vs. Pentagon standoff can be seen as both a contractual dispute and another skirmish in the never-ending culture war that has consumed public
Read essayLiving With a Personal Agent
Last week I introduced Saarthi, my OpenClaw agent. I've been adding tasks steadily: synthesizing newsletters, monitoring prediction markets, writing more
Read essayAnthropic, the Pentagon, and the Judgment of Future Claude
I have many takes on the Anthropic / Pentagon contract situation. But I won’t talk politics here. Since it’s the weekend, let’s turn on the lava lamp, and
Read essayWhen Your App Becomes a Context Provider
Last week, I gave Claude access to my reading life.
Read essayContext Engineering as Narration
User profiles are stories compressed into spreadsheets. LLMs let us uncompress them. This is both a context engineering challenge and a storytelling one.
Read essayThe Lego Model: How Tool Calling Changes the Way We Build AI Applications
"What should I read next?" seems like a simple question. But answering it well requires knowing what the user is currently reading, what they've finished
Read essayBuilding at the Speed of Thought
On building QuietReads, Claude Code, and the inversion in software economics
Read essayThe Same Window For Everything
I've been thinking about how I use AI tools lately. They're clearly useful. What interests me is how the experience feels.
Read essayIlya Sutskever, the Scaling Hypothesis, and the Art of Talking Your Book
If you've just raised $3 billion to build a new god, it helps to question the faith in the old one.
Read essayIs Your AI Playing Roulette, Poker, or War?
On May 6, 2010, the Dow Jones dropped nearly 1,000 points in minutes. A trillion dollars vanished. And then the market bounced back. The whole thing took
Read essayPrompting Is All You Need
Agents are supposed to be the future of how we build AI software. I am not so sure.
Read essayWhy is LLM writing so weird?
AI writing is strange. The models continue to improve, yet they still struggle to cross the uncanny valley that separates AI-generated content from
Read essay5 Mental Models to understand the current AI Moment.
Goodhart's Law: "When a measure becomes a target, it ceases to be a good measure."AI usage is a terrible metric. Using AI for what? We end up with initiatives
Read essayBuilding a Truth-Seeking AI is a Sisyphean Endeavor
Elon Musk's goal for xAI's Grok model is to be "maximally truth-seeking." When Grok generated responses that were not aligned with Musk's ideas of Truth, he
Read essayReview: If Anyone Builds It, Everyone Dies
by Elizier Yudkowsky and Nate Soares (2025)
Read essayWe’re DDoS-ing ourselves with AI Slop.
A DDoS (Distributed Denial of Service) attack overwhelms a scarce resource with a flood of traffic, making it unavailable to its intended users.
Read essayHow do LLMs understand Gujarati?
One of my favorite ways of testing LLM-powered apps at Jeavio is to ask them questions in transliterated Hindi or Gujarati. I ask questions in Latin script
Read essayWhy do LLMs hallucinate?
Your palms are sweaty, knees are weak, arms are heavy - it’s not a rap battle but a test for a class which you may or may not have slept through for the
Read essayMIT Study – 95% of Generative AI Investments Fail (or do they?)
MIT released a study showing that 95% of organizations are getting zero return from their GenAI investments.
Read essayRoadtrippin’
Fifteen hours alone in a minivan will take your mind to strange places.Last weekend, as I drove from the Gulf Shore back home, mine wandered from gas station
Read essayDo agentic coding tools make us less productive?
Are agentic coding tools like Cursor making us less productive?
Read essayAgency and LLMs as Mentors
Cate Hall, writing on Substack, suggested that a way to do hard things is to ask "What would someone 10x better do?" and then do it. Reading the post made me
Read essayWhat is a vibe coder really?
20+ years ago, in my first job (junior business analyst - first class), I developed two critical skills: the ability to type fast and the ability to click
Read essayTo replit or not to replit ..
As a summer treat to myself, I spent a few bucks on replit to build a GoodReads style app - just so I could do a vibe-check on the current state of .. vibe
Read essayChatGPT rotting your brain? .. maybe?
“For this invention will produce forgetfulness in the minds of those who learn to use it, because they will not practice their memory. Their trust in writing,
Read essayAI, Friction, and Credibility
I got caught in a thunderstorm just outside the town of Lovettsville, VA on Friday. I pulled into a gas station and spent thirty minutes in the company of a
Read essayBuilding hyper-personalized AI Apps..
I'm a PowerPoint jockey and a very rusty programmer. Yet, over the weekend, I built something that had been an idea for years.
Read essayAI safety in 2025
Two years ago, the Future of Life Institute called for a 6-month pause in AI development due to fears of misalignment. Elon Musk and hundreds of other
Read essayAgentic coding tools and the problems of agency
Claude Code, OpenAI Codex and other agentic coding tools have a problem with .. “agency”.
Read essayDispatches from Mediocristan
LLMs are powerful tools - but credulous users risk being stuck in a dangerous place: Mediocristan, the land of the average.
Read essayThe AI Leadership Paradox: When Slowing Down Becomes a Competitive Advantage
AI tools are supercharging individual productivity—but are they also undermining team cohesion?
Read essayNegotiating with a strange peer ..
An under-appreciated facet of LLMs is just how *weird* they are.
Read essayMelanie Mitchell on the Turing Test
From "The Turing test and our shifting conceptions of intelligence" by Melanie Mitchell.
Read essaySmallville, Agent Based Modeling, and Capital Markets
Google and Stanford cooked up something intriguing—a virtual village called Smallville, populated by agents running on the #ChatGPT API.
Read essayGenerative Models and the “Grey Goo Problem”
Generative AI models may be causing a "Grey Goo" problem with art, publishing, and user-generated content.
Read essay